Hugging Face's logo

tensorblock
/
granite-3.1-2b-base-GGUF

Transformers
GGUF
language
granite-3.1
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
morriszms commited on
Commit
308b923
·
verified ·
1 Parent(s): 19e0598

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +79 -0
  3. granite-3.1-2b-base-Q2_K.gguf +3 -0
  4. granite-3.1-2b-base-Q3_K_L.gguf +3 -0
  5. granite-3.1-2b-base-Q3_K_M.gguf +3 -0
  6. granite-3.1-2b-base-Q3_K_S.gguf +3 -0
  7. granite-3.1-2b-base-Q4_0.gguf +3 -0
  8. granite-3.1-2b-base-Q4_K_M.gguf +3 -0
  9. granite-3.1-2b-base-Q4_K_S.gguf +3 -0
  10. granite-3.1-2b-base-Q5_0.gguf +3 -0
  11. granite-3.1-2b-base-Q5_K_M.gguf +3 -0
  12. granite-3.1-2b-base-Q5_K_S.gguf +3 -0
  13. granite-3.1-2b-base-Q6_K.gguf +3 -0
  14. granite-3.1-2b-base-Q8_0.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ granite-3.1-2b-base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ granite-3.1-2b-base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ granite-3.1-2b-base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ granite-3.1-2b-base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ granite-3.1-2b-base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ granite-3.1-2b-base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ granite-3.1-2b-base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ granite-3.1-2b-base-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ granite-3.1-2b-base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ granite-3.1-2b-base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ granite-3.1-2b-base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ granite-3.1-2b-base-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - language
6
+ - granite-3.1
7
+ - TensorBlock
8
+ - GGUF
9
+ base_model: ibm-granite/granite-3.1-2b-base
10
+ ---
11
+
12
+ <div style="width: auto; margin-left: auto; margin-right: auto">
13
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
14
+ </div>
15
+ <div style="display: flex; justify-content: space-between; width: 100%;">
16
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
18
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
19
+ </p>
20
+ </div>
21
+ </div>
22
+
23
+ ## ibm-granite/granite-3.1-2b-base - GGUF
24
+
25
+ This repo contains GGUF format model files for [ibm-granite/granite-3.1-2b-base](https://huggingface.co/ibm-granite/granite-3.1-2b-base).
26
+
27
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4391](https://github.com/ggerganov/llama.cpp/commit/9ba399dfa7f115effc63d48e6860a94c9faa31b2).
28
+
29
+ <div style="text-align: left; margin: 20px 0;">
30
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
31
+ Run them on the TensorBlock client using your local machine ↗
32
+ </a>
33
+ </div>
34
+
35
+ ## Prompt template
36
+
37
+ ```
38
+
39
+ ```
40
+
41
+ ## Model file specification
42
+
43
+ | Filename | Quant type | File Size | Description |
44
+ | -------- | ---------- | --------- | ----------- |
45
+ | [granite-3.1-2b-base-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q2_K.gguf) | Q2_K | 0.978 GB | smallest, significant quality loss - not recommended for most purposes |
46
+ | [granite-3.1-2b-base-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q3_K_S.gguf) | Q3_K_S | 1.130 GB | very small, high quality loss |
47
+ | [granite-3.1-2b-base-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q3_K_M.gguf) | Q3_K_M | 1.252 GB | very small, high quality loss |
48
+ | [granite-3.1-2b-base-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q3_K_L.gguf) | Q3_K_L | 1.357 GB | small, substantial quality loss |
49
+ | [granite-3.1-2b-base-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q4_0.gguf) | Q4_0 | 1.453 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
50
+ | [granite-3.1-2b-base-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q4_K_S.gguf) | Q4_K_S | 1.464 GB | small, greater quality loss |
51
+ | [granite-3.1-2b-base-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q4_K_M.gguf) | Q4_K_M | 1.545 GB | medium, balanced quality - recommended |
52
+ | [granite-3.1-2b-base-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q5_0.gguf) | Q5_0 | 1.757 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
53
+ | [granite-3.1-2b-base-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q5_K_S.gguf) | Q5_K_S | 1.757 GB | large, low quality loss - recommended |
54
+ | [granite-3.1-2b-base-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q5_K_M.gguf) | Q5_K_M | 1.805 GB | large, very low quality loss - recommended |
55
+ | [granite-3.1-2b-base-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q6_K.gguf) | Q6_K | 2.081 GB | very large, extremely low quality loss |
56
+ | [granite-3.1-2b-base-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.1-2b-base-GGUF/blob/main/granite-3.1-2b-base-Q8_0.gguf) | Q8_0 | 2.694 GB | very large, extremely low quality loss - not recommended |
57
+
58
+
59
+ ## Downloading instruction
60
+
61
+ ### Command line
62
+
63
+ Firstly, install Huggingface Client
64
+
65
+ ```shell
66
+ pip install -U "huggingface_hub[cli]"
67
+ ```
68
+
69
+ Then, downoad the individual model file the a local directory
70
+
71
+ ```shell
72
+ huggingface-cli download tensorblock/granite-3.1-2b-base-GGUF --include "granite-3.1-2b-base-Q2_K.gguf" --local-dir MY_LOCAL_DIR
73
+ ```
74
+
75
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
76
+
77
+ ```shell
78
+ huggingface-cli download tensorblock/granite-3.1-2b-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
79
+ ```
granite-3.1-2b-base-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e008e5136de21d28052868e4c7de1a8cbc5a19a88a8439e3e92cf80d2176526e
3
+ size 978236224
granite-3.1-2b-base-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2eafb9276e6bfcb7dc1cbe2c61ce158145a48ee5af37fb4c2e6cd802b53dd0a
3
+ size 1357361984
granite-3.1-2b-base-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc580c9a067eb99a3f33aa85200d9b0e314a3b7b98ab3d546a7db4bb1d1351e
3
+ size 1251717952
granite-3.1-2b-base-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec253c0416340cb7c0a2f42f430b741e2a5863dbb05c30dba187f84afa40252
3
+ size 1130279744
granite-3.1-2b-base-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e790d0b2d2db635339f78603dc977583e56ffd3f19e22678511b67ab944086d8
3
+ size 1453372224
granite-3.1-2b-base-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42647ea7909fba4ae03130d28d5d0e769521c00494672cd4e61044436068f89c
3
+ size 1545286464
granite-3.1-2b-base-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd58bdd021a738843cd07e80b9d004cea08b63169ed86d38144a011f6b3abc05
3
+ size 1464382272
granite-3.1-2b-base-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:929f463a95403d9af47aeacc1213a00fa9a0a1b5a5052acf004c09d49909f63d
3
+ size 1757459264
granite-3.1-2b-base-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d38fb6a8f2373de524985a1e04bb36512a914c0ad4392995ceef55105f10244
3
+ size 1804809024
granite-3.1-2b-base-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf51c2c1748cf2581b6d7e17464776950dc4fa96dbc929fe9642d7bd592af03a
3
+ size 1757459264
granite-3.1-2b-base-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a363de0292250407cd2220010ddae98c3c02c6de67fb98e657287b46640459
3
+ size 2080551744
granite-3.1-2b-base-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2827771ab1401c055a9fc3a410530e69370915edabdd67c4d737850850174051
3
+ size 2694099776